Emotion Detection Techniques for the Evaluation of Serendipitous Recommendations

Recommender systems analyze a users past behavior, build a user profile that stores information about her interests, maybe find others who have a similar profile, and use that information to find potentially interesting items. The main limitation of this approach is that the user will be provided with items within her existing range of interests and her tendency towards a certain behavior will be reinforced by creating a self-referential loop. This drawback is known as overspecialization or serendipity problem. New methods are required to find unexpected suggestions that help the user to find surprisingly interesting items that she might not have otherwise discovered, or it would have been really hard to discover. The evaluation of these techniques is not simple: there is a level of emotional response associated with serendipity that is difficult to measure. In this chapter we describe a user study to assess both the acceptance and the perception of serendipitous recommendations, through the administration of questionnaires and the analysis of users emotions. Facial expressions of users receiving recommendations are analyzed to evaluate whether they convey a mixture of emotions that helps to measure the perception of serendipity of recommendations. The results showed that positive emotions such as happiness and surprise are associated with serendipitous suggestions